| Output $/MTok | $6.00 | $0.28 |
|---|---|---|
| Input $/MTok | $2.00 | $0.14 |
| Cached input $/MTok | $0.3000 | $0.0028 |
| Context window | 500,000 | 1,048,576 |
| Output cap | 500,000 | 384,000 |
| Modalities | in: text, image / out: text | in: text / out: text |
| Tool use | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Family | Grok 4 | DeepSeek V3 |
| Knowledge cutoff | 2026-02-01 | — |
| Verified | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ |
| $/min | $0.003300 |
|---|---|
| $/min batch | — |
| Streaming | — |
| Realtime | — |
| Languages | en |
| Diarization | included |
| TTFW | — |
| Verified | 2026-07-19 |
| Source | provider page ↗ |
| $/1M chars | $30.00 | $50.00 | $19.50 |
|---|---|---|---|
| Voice quality | neural | neural | neural |
| Voice cloning | — | ✓ included | — |
| Voice count | — | — | — |
| Languages | en, es, de, fr, nl, it, ja | 31+ | en, hi, mr, ta, ml, te, kn, pa, bn, or, gu, ar, zh, id, ja, ko, ms, tr, vi, de, es, fr, it, pt, ru, el, fi, no, pl |
| SSML support | — | — | — |
| TTFB | — | — | 200ms |
| Output formats | wav, mp3, linear16, mulaw, alaw, opus | — | pcm, mp3, wav, ulaw, alaw |
| Verified | 2026-07-19 | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ | provider page ↗ |